What you get

A prompt that turns any LLM into a meticulous senior engineer reviewing your code. It checks for:

• Bugs and edge cases — null checks, off-by-one errors, race conditions
• Architecture concerns — coupling, separation of concerns, SOLID violations
• Readability — naming, function length, comment quality
• Performance — unnecessary re-renders, N+1 queries, memory leaks

Output format

The review comes as a structured list with severity levels (critical / warning / suggestion) and specific line references.